© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 22057
    Prev
    Next
    INDEX
    Explanations

    words related to lenses and photography

    oai_token-act-pair · gpt-3.5-turbo

    mentions of optical lenses or related optical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TY
    -0.76
    lly
    -0.73
    BY
    -0.72
    anqu
    -0.64
    icted
    -0.64
     Chatt
    -0.63
    querque
    -0.63
    DIT
    -0.62
     quo
    -0.62
    onge
    -0.60
    POSITIVE LOGITS
     lens
    1.06
     flares
    1.05
     lenses
    1.02
     flare
    0.95
    Cra
    0.91
    linger
    0.90
    Lens
    0.86
    horn
    0.85
    ner
    0.84
     Lens
    0.84
    Activations Density 0.021%

    No Known Activations